© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 59445
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elop
    -0.07
    λιά
    -0.07
    @store
    -0.06
    beiten
    -0.06
    esch
    -0.06
    _Native
    -0.06
    ìĻĦ
    -0.06
    äter
    -0.06
     integr
    -0.06
    swick
    -0.06
    POSITIVE LOGITS
    ayah
    0.07
    _operand
    0.06
    _hint
    0.06
    oose
    0.06
    Eventually
    0.06
    MLE
    0.06
     æĶ¶
    0.06
     bonne
    0.06
    nob
    0.06
    é±
    0.06
    Activations Density 0.000%

    No Known Activations